Meltemi 7B Instruct (Chios dialect) — MLX 4-bit (fused)
This is an MLX-converted 4-bit Meltemi model with a Chios-dialect LoRA adapter fused in, so you can run it without specifying --adapter-path.
The training corpus was built from the pdf24_ocrPdf/ OCR PDFs and cleaned to contain only Greek / polytonic Greek letters (no Latin characters).
Usage
python -m mlx_lm chat --model YOUR_LOCAL_FOLDER_OR_HF_REPO --system-prompt "Μίλα πάντα στη χιώτικη διάλεκτο."
- Downloads last month
- 8
Model size
1B params
Tensor type
BF16
·
U32
·
Hardware compatibility
Log In
to add your hardware
4-bit
Model tree for ASiatras/Chios_Chatbot
Base model
ilsp/Meltemi-7B-Instruct-v1